Simulation correction using measurements and deep learning

Abstract

A method for improving the accuracy of simulation models can include measuring a characteristic value at one or more nodes of a physical embodiment corresponding to the simulation model; inputting the measured characteristic value into a trained machine learning facility corresponding to the simulation model; and receiving from the trained machine learning facility one or more predicted values based at least in part on the inputted measured characteristic value.

We claim: 
     
         1 . A method for adjusting a simulation model, the method comprising:
 measuring a characteristic value at one or more nodes of a physical embodiment corresponding to the simulation model;   inputting the measured characteristic value into a trained machine learning facility corresponding to the simulation model; and   receiving from the trained machine learning facility one or more predicted values based at least in part on the inputted measured characteristic value.   
     
     
         2 . The method for adjusting a simulation model of  claim 1 , further comprising:
 modifying at least a portion of the simulation model based at least in part on the one or more received predicted values to generate a modified simulation model.   
     
     
         3 . The method for adjusting a simulation model of  claim 1 , further comprising:
 modifying at least a portion of the modified simulation model based at least in part on another predicted value received from the trained machine learning facility to generate a further modified simulation model.   
     
     
         4 . The method for adjusting a simulation model of  claim 1 , further comprising training the machine learning facility. 
     
     
         5 . The method for adjusting a simulation model of  claim 4 , in which training the machine learning facility comprises:
 receiving information for at least one parameter of at least one component of the simulation model; and   inputting a set of training data to the machine learning facility that includes generated simulated values associated with the at least one parameter of the at least one component of the simulation model.   
     
     
         6 . The method for adjusting a simulation model of  claim 4 , in which the set of training data comprises a set of training data created using Monte Carlo simulations. 
     
     
         7 . The method for adjusting a simulation model of  claim 1 , in which the simulation model is a circuit simulation model, and wherein the circuit simulation model includes at least one component selected from the group consisting of: a resistor, a transistor, a capacitor, an inductor, a diode, an operational amplifier, a voltage source, a current source, and a transmission line. 
     
     
         8 . The method for adjusting a simulation model of  claim 1 , in which the simulation model is a circuit simulation model, and wherein the at least one parameter is selected from the group consisting of: resistance, impedance, temperature coefficient, parasitic capacitance, transmission line length, transmission line width, material dielectric constant, and geometry. 
     
     
         9 . The method for adjusting a simulation model of  claim 2 , in which modifying at least a portion of the circuit simulation model comprises replacing the simulation model that is stored in a memory with the modified simulation model. 
     
     
         10 . The method for adjusting a simulation model of  claim 1 , wherein the simulation model is a circuit simulation model, a three-dimensional electromagnetic model, a serial data link simulation model, a thermal simulation model, or a motion simulation model. 
     
     
         11 . The method for adjusting a simulation model of  claim 10 , wherein the simulation model is a SPICE circuit simulation model. 
     
     
         12 . A test and measurement system, comprising:
 a machine configured to host a machine learning facility; and   a test and measurement instrument having one or more processors configured to:
 measure a characteristic value at one or more nodes of a physical instance built according to a simulation model; 
 input the measured characteristic value into a trained machine learning facility corresponding to the simulation model; and 
 receive from the trained machine learning facility one or more predicted values based at least in part on the inputted measured characteristic value. 
   
     
     
         13 . The test and measurement system of  claim 12 , wherein the one or more processors are further configured to improve the simulation model based at least in part on the received predicted value to generate an improved simulation model. 
     
     
         14 . The test and measurement system of  claim 12 , wherein the one or more processors are further configured to:
 receive information for at least one parameter of at least one component of a simulation model; and   input a set of training data to the machine learning facility that includes generated simulated values associated with the at least one parameter of the at least one component of the simulation model.   
     
     
         15 . The test and measurement system of  claim 12 , in which the simulation model is a circuit simulation model, and wherein the at least one parameter is selected from the group consisting of: resistance, impedance, temperature coefficient, parasitic capacitance, transmission line length, transmission line width, material dielectric constant, and geometry. 
     
     
         16 . The test and measurement system of  claim 12 , further comprising a memory configured to store the simulation model. 
     
     
         17 . The test and measurement system of  claim 16 , wherein the one or more processors are further configured to:
 further improve the simulation model based at least in part on the at least one received predicted value for the improved simulation model.   
     
     
         18 . The test and measurement system of  claim 12 , wherein the machine learning facility is structured to operate on one of the one or more processors of the test and measurement instrument. 
     
     
         19 . The test and measurement system of  claim 12 , wherein the machine learning facility is structured to operate a processor separate from the one or more processors of the test and measurement instrument. 
     
     
         20 . The test and measurement system of  claim 12 , wherein the simulation model is a circuit simulation model, a three-dimensional electromagnetic model, a serial data link simulation model, a thermal simulation model, or a motion simulation model.